COSC 579: Computer Vision

Student Project Submissions (Exercise #3)

Morphing Videos:

Camera Obscura:

Image Stiching:

Instructor

Jeremy Bolton: Teaching and Research

Course Calendar

Final Project Topics

Pre determined topics:

Disparity Map via Graph: [Roy] [Boykov]
Image Segmentation via Graph: [Boykov]
Active Contours - Snakes: [Kass]
CNNs (Caffe or other) : [Jia]
Multiple Instance Learning in Computer Vision: [Maron]

Books

Computer vision:

[Sz] Szeliski, Computer Vision: Algorithms and Applications, Springer, 2010
[Pc] Prince, Computer Vision Models, Cambridge University Press, 2012
[Hn] Horn, Robot Vision, MIT Press, 1986
[FP] Forsyth and Ponce, Computer Vision: A Modern Approach, Prentice Hall, 2002

Learning:

[GBC] Goodfellow, Bengio and Courville, Deep Learning, MIT Press, 2016
[Nl] Neilson, Neural Networks and Deep Learning, MOOT
[DHS] Duda, Hart and Stork, Pattern Classification (2nd Edition), Wiley-Interscience, 2000
[Bp] Bishop, Pattern Recognition and Machine Learning , Spring, 2006

Topic Schedule

Many of the slides and presentations are modified from course textbooks and the excellent class notes of similar courses offered in other schools by some of the following professor and researchers Yung-Yu Chuang, Fredo Durand, Alexei Efros, William Freeman, James Hays, Svetlana Lazebnik, Andrej Karpathy, Fei-Fei Li, Srinivasa Narasimhan, Silvio Savarese, Steve Seitz, Noah Snavely, Richard Szeliski, and Li Zhang. The instructor is extremely thankful to the researchers for making their notes available online. Please feel free to use and modify any of the slides, but acknowledge the original sources where appropriate.

The following schedule is sequentially organized by topics and subject to change. We will cover approximately 1 topic per day, but this will vary.

SEE CANVAS FOR SUBMISSION AND DUE DATES

Topic	Topic/notes	Readings	Assignments, etc.
0	Introduction and Overview [ppt \| pdf]	[Sz] 1
1	Camera and Scene Geometry [ppt \| pdf]	[Sz] 2.1 [Pc] 14 [GBC] 2: LA Review [FP] 1.2	Assignment #1 [sol]
2	Radiometry [ppt \| pdf]	[Sz] 2.2, 2.3
3	Color [ppt \| pdf]	[Sz] 2.2, 2.3	Assignment #2 text image
4	Image Acquisition and Representation [ppt \| pdf]	[Sz] 2.3
5	Image Warping: Align and Mosaic [ppt \| pdf ] and Morphing [ppt \| pdf ]	[Sz] 3.6, 6.1, 9.1, and 9.3 image morphing Delauney Tri. Gartner, Hoffman	Assignment #3 morph images
6	Stereopsis and Binocular Reconstruction [ppt \| pdf ]	[Sz] 2.1, 7.1, 7.2, 11.1, 11.4, 11.5 [FP] 7.1, 7.2 [Hn] 13.1 Bolles Section 1 IllPosedness
7	Point Operators and Linear Filters [ppt \| pdf ]	[Sz] 3.1 [Pc] 13.1
	Invited Speaker: Rama Chellappa: Deep Learning Networks for Computer Vision CS Department Seminar: Friday 9/29 @11AM in STM 326	paper
8	Edge Detection: Gradient, Laplacian, and Scale Space[ppt \| pdf ]	[Sz] 4.2 Marr - Hildreth Witkin: Scale Space	Assignment #4 [sol]
9	Texture [ pdf ]	[Sz] 3.4, 4.1, and 4.3
	Exam #1	Disparity Notes DP	Exam #1
10	Features and Feature matching [ pdf ]	[Sz] 6.1
11	Image Segmentation: Graph Based Models[ pdf ]	[Sz] 5 Kass	Final Project
12	Active Contours: Snakes [ pdf ]	[Sz] 5 [Kass]
13	Machine Learning and Pattern Recognition in Computer Vision [ pdf ]	[Sz] 14 [Pc] 6, 8.1 - 8.4, 9.1 - 9.3
14	Multiple Instance Learning in Vision	[Sz] 14.4, 14.5 [Pc] 20 [Maron]
15	Convolutional Neural Networks [pdf]	[Nl] 1 - 6 [LeCun]
16	Object Recognition Example: Eigenfaces [pdf]	[Sz] 14 [Sirovich] [Turk]
17	Invited Speaker: Spencer Whitehead , November 28 (in-class) Learning to Desribe Videos	Image captioning with attention
	Final Project Presentations	See course calendar	ppt
	Final Project Presentations	See course calendar
	Final Project Presentations	See course calendar

Resources

Image datasets:

Labelme: an online annotation tool to build image databases for computer vision research
OpenSurfaces: a large database of annotated surfaces created from real-world consumer photographs.
SUN Database: a benchmark for scene recognition and object detection with annotated scene categories and segmented objects
Places Database: a scene-centric database with 205 scene categories and 2.5 millions of labelled images
NYU Depth Dataset v2: a RGB-D dataset of segmented indoor scenes
Microsoft COCO: a new benchmark for image recognition, segmentation and captioning
Flickr100M: 100 million creative commons Flickr images
Labeled Faces in the Wild: a dataset of 13,000 labeled face photographs
Human Pose Dataset: a benchmark for articulated human pose estimation
YouTube Faces DB: a face video dataset for unconstrained face recognition in videos
UCF101: an action recognition data set of realistic action videos with 101 action categories
HMDB-51: a large human motion dataset of 51 action classes

Top computer vision conferences (calendar ) and papers:

CVPR: IEEE Conference on Computer Vision and Pattern Recognition
ICCV: International Conference on Computer Vision
ECCV: European Conference on Computer Vision
NIPS: Neural Information Processing Systems

Other resources: